1 / 23

Social Action Tracking via Noise Tolerant Time-varying Factor Graphs

Social Action Tracking via Noise Tolerant Time-varying Factor Graphs. 1 Chenhao Tan, 1 Jie Tang, 2 Jimeng Sun, 3 Quan Lin , 4 Fengjiao Wang 1 Department of Computer Science and Technology, Tsinghua University, China 2 IBM TJ Watson Research Center, USA

hasad
Download Presentation

Social Action Tracking via Noise Tolerant Time-varying Factor Graphs

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Social Action Tracking via Noise Tolerant Time-varying Factor Graphs 1Chenhao Tan,1Jie Tang, 2JimengSun, 3Quan Lin, 4FengjiaoWang 1Department of Computer Science and Technology, Tsinghua University, China 2IBM TJ Watson Research Center, USA 3Huazhong University of Science and Technology, China 4Beijing University of Aeronautics and Astronautics, China

  2. Motivation • 500 millionusers • the 3rd largest “Country” in the world • More visitors than Google • Action: Update statues, create event • More than 4billion images • Action: Add tags, Add favorites • 2009, 2 billiontweets per quarter • 2010, 4 billiontweets per quarter • Action: Post tweets, Retweet

  3. User Action in Social Networks Arnetminer Twitter Flickr Post tweets on “Haiti Earthquake” Publish in KDD Conference Add photo to her favorites

  4. User Action in Social Networks • Questions: • What factors influence you to add a photo into your favorite list? • - If you post a tweet on “Haiti Earthquake”, will your friends retweet it or reply? • Challenge: • - How to track and model users’ actions? • - How to predict users’ actions over time?

  5. Complex Factors Action Prediction: Will John post a tweet on “Haiti Earthquake”? Influence Correlation 1 3 Time t+1 Time t John John Personal attributes Attributes: Always watch news Enjoy sports …. 4 Dependence 2

  6. Problem formulation Gt =(Vt, Et, Xt, Yt) Actions at time t Nodes at time t Edges at time t Attribute matrix at time t

  7. NTT-FGM Model Influence Correlation Continuous latent action state Personalattributes Dependence Action Personal attributes

  8. Model Instantiation How to estimate the parameters?

  9. Model Learning • Extremely time costing!! • Our solution: distributed learning (MPI)

  10. Experiment • Data Set • Baseline • SVM • wvRN (Macskassy, 2003) • Evaluation Measure: Precision, Recall, F1-Measure

  11. Performance Analysis

  12. Factor Contribution Analysis • NTT-FGM: Our model • NTT-FGM-I: Our model ignoring influence • NTT-FGM-CI: Our model ignoring influence and correlation

  13. Efficiency Performance

  14. Conclusion • Formally formulate the problem of social action tracking • Propose a unified model: NTT-FGM to simultaneously model various factors • Present an efficient learning algorithm and develop a distributed implementation • Validate the proposed approach on three different data sets, and our model achieves a better performance

  15. Thank you! QA? Data & Code: http://arnetminer.org/stnt Welcome to our poster!

  16. Statistical Study: Influence Y-axis: the likelihood that the user also performs the action at t X-axis: the percentage of one’s friends who perform an action at t − 1

  17. Statistical Study: Dependence Y-axis: the likelihood that a user performs an action X-axis: different time windows

  18. Statistical Study: Correlation Y-axis: the likelihood that two friends(random) perform an action together X-axis: different time windows

  19. Appendix

  20. Appendix

  21. Appendix

  22. Prediction • Based on the learning parameters we just need to solve the following equations:

  23. Latent State Analysis Action Bias Factor: f(y12|z12) Influence Factor: g(z11,z12) Correlation Factor: h(z12,z22), h(z12,x12)

More Related